codex tip: give codex a clear outcome to work towards tell codex what you want to achieve, how it can verify it got there, then let it keep going until it does for example: “make the build faster” is quite vague “measure the production build on vercel, keep going until it’s
SOFTWARE
-
Harvard collaboration study of Perplexity Computer shows efficiency and autonomy
By
–
We're sharing a comprehensive study of Perplexity Computer in real-world deployment in collaboration with Harvard Computer is more cost and time-efficient, unlocks cross-disciplinary search beyond the reach of multi-step search, and provides higher autonomy and quality in the
-
Videos created for every feed and format with Aleph 2.0
By
–
One video, now made for every feed and format. Upload your existing video, choose your desired aspect ratio and watch our editing model, Aleph 2.0, fill in the rest of the scene as if you made it that way from the start.
— Runway (@runwayml) 8 juin 2026
Try it on our desktop web app at the link below. pic.twitter.com/EdPkUEc2BSA video, now created for every feed and format. Upload your existing video, choose the desired aspect ratio and watch our editing model, Aleph 2.0, complete the rest of the scene as if you had made it that way from the start. Try it on our
-
NotebookLM: upcoming updates with Gemini 3.5 and Omni
By
–
NotebookLM updates soon We are expecting Gemini 3.5 Flash and Gemini Omni upgrades, along with a bunch of new features. Which ones do you want the most?
-
WWDC 2026: Apple to use Google’s 1.2T-parameter Gemini for Siri
By
–
WWDC 2026 – Apple rents Google's brain to fix Siri. What we can expect: Apple's keynote today is a software reset built around one admission: it couldn't build frontier AI alone. What to expect: – Gemini-powered Siri, a rebuilt assistant on a custom 1.2T-parameter Google model,
-
Hivemind launches continual learning for AI coding agents
By
–
New from Hivemind: continual learning for AI coding agents, available to everyone starting today.
— Chubby♨️ (@kimmonismus) 8 juin 2026
It takes the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, Pi) and turns them into reusable skills, then pushes those skills across all of them, all on… https://t.co/MFS1ZpCh4DNew from Hivemind: continual learning for AI coding agents, available to everyone starting today. It takes the traces from every agent your team runs (Claude Code, Codex, Cursor, Hermes, Pi) and turns them into reusable skills, then pushes those skills across all of them, all on
-
Kimi for Work AI Agent with Native Swarm and Browser Use
By
–
KIMI 🔥: A new "Kimi for Work" AI Agent has been released with support for Native Agent Swarm, Browser Use, and more!
— 🚨 AI News | TestingCatalog (@testingcatalog) 8 juin 2026
> The app is available on both macOS and Windows.
> Users can spawn up to 300 agents locally.
> Browser Use is working as part of the earlier-released… https://t.co/sR385ghZUU pic.twitter.com/o9fttZQyxyKIMI : A new "Kimi for Work" AI Agent has been released with support for Native Agent Swarm, Browser Use, and more! > The app is available on both macOS and Windows. > Users can spawn up to 300 agents locally.
> Browser Use is working as part of the earlier-released -
AI Spend Controls Proactive Budget Alerts for Workloads
By
–
AI workloads create new cost management challenges, from runaway retry loops to uncontrolled agent experimentation.
— Databricks (@databricks) 8 juin 2026
AI Spend Controls in Unity AI Gateway introduce proactive budget alerts across users, workspaces, use cases, and entire accounts so organizations can monitor and… pic.twitter.com/2H7OHs5sCiAI workloads create new cost management challenges, from runaway retry loops to uncontrolled agent experimentation. AI Spend Controls in Unity AI Gateway introduce proactive budget alerts across users, workspaces, use cases, and entire accounts so organizations can monitor and
-
ElevenLabs partners with UK to improve public service access via Voice AI
By
–
Voice AI will fundamentally improve access to public services. We're partnering with the UK Government to make it easier to access information and services online – especially for people who are visually impaired, struggle to read, or have difficulty navigating the internet.
-
Coding agent retry loop: 10,000 calls huge bill
By
–
A coding agent gets stuck in a retry loop during the night. By morning, it has made 10,000 LLM calls. You now have a four-digit bill. Observability tells you what happened, but stopping these problems before they